#INTERSPEECH2023

Elles comme Linguistesellescommelinguistes
2023-08-30

Our paper is now online!

Hutin, M., Degand, L., Allassonnière-Tang, M. (2023) Investigating the Syntax-Discourse Interface in the Phonetic Implementation of Discourse Markers. Proc. INTERSPEECH 2023, 2563-2567, doi: 10.21437/Interspeech.2023-1619

isca-speech.org/archive/inters

halcy​ :icosahedron:halcy@icosahedron.website
2023-08-24

anyways, goodbye, #INTERSPEECH, it was a really interesting four days! #INTERSPEECH2023

Dublin Convention Center with the INTERSPEECH banner
halcy​ :icosahedron:halcy@icosahedron.website
2023-08-23

best paper at #INTERSPEECH this year? #INTERSPEECH2023

A poster comparing source code availability at various conferences. INTERSPEECH isn’t doing so hot. Positively, trend is up, across all conferences.
Rozenn Dahyot ✅️RDahyot
2023-08-21

InterSpeech 2023 is starting this week in sunny Dublin ! interspeech2023.org

Congratulations to Sam Kotey presenting her work there on "Query Based Acoustic Summarization for Podcasts"

doi.org/10.21437/Interspeech.2

@AdaptCentre

Our proposed query based clustering framework:
Clusters are initiated with the query and each embedding is assigned
a local similarity score. A global score is obtained from
the mean of the cluster’s local scores. The predicted cluster
has the maximum global score and snippets are used to create
a summary.
halcy​ :icosahedron:halcy@icosahedron.website
2023-08-21

Anyways if anyone else is here, do hit me up! #INTERSPEECH2023 #Interspeech

halcy​ :icosahedron:halcy@icosahedron.website
2023-08-21

Finally at #INTERSPEECH2023 !

INTERSPEECH 2023 opening session
Tom Kentertom_kenter
2023-08-17

Interesting paper (I think ;-)) on using MOS scores vs side-by-side preference tests when comparing TTS systems.

How to choose? Is one more robust/sensitive than the other?

Ever wondered about that?

Here is the paper:

tomkenter.nl/pdf/camp2023_comp

halcy​ :icosahedron:halcy@icosahedron.website
2023-07-06

Travel booked for #INTERSPEECH2023 !

Anyone else here going?

#INTERSPEECH2023 #INTERSPEECH #ISCA #IS2023

halcy​ :icosahedron:halcy@icosahedron.website
2023-05-24

Today, we're releasing our #audio #speech quality assessment model for the audio packet-loss concealment ( #plc ) task, so you, too, can stop using mediocre metrics like PESQ and POLQA! #science

github.com/microsoft/PLC-Chall

Paper to appear at #INTERSPEECH2023 #interspeech , preprint for now: halcy.de/cites/papers/diener20 , arxiv soon

2023-02-20

Baseline system + leaderboards are up for #MerlionChallenge untangling complex code-mixed speech. Which #ML #DeepLearning #SpeechProc system will do the best job on complex language use in the wild? 👀

TWO TEAMS have already beaten the baseline for Language ID:
🎉Lingua_Lumos (Closed)
🎉UNSW_Signal_Processing (Open)

There’s still time to join the challenge and prep your paper for our special session at #Interspeech2023

toot.community/@suzyjstyles/10

Title text: MERLIon CCS Leaderboards: Task 1
Subtitle: The MERLIon CCS Challenge is a speech processing challenge for Interspeech 2023. Task 1: Language Identification. All participating teams must submit a model to Task 1 (Closed). Task 2 is optional. *+ + DID YOU KNOW? + + With the body of a mermaid and the head of a lion, the Merlion is a national icon of Singapore. * Just as the Merlion is a mix of different creatures, the code-switched child-directed speech in this challenge is a mix of different languages 
Left panel: MERLIon CCS Task 1 Closed 
Codalab leaderboard First place: Lingua_Lumos.
Left panel: MERLIon CCS Task 2 Open 
Codalab leaderboard First place: UNSW_Signal_Processing

Client Info

Server: https://mastodon.social
Version: 2025.04
Repository: https://github.com/cyevgeniy/lmst